Update README.md

README.md

@@ -9,12 +9,14 @@ inference: true
 
 ---
 
-# Anime Diffusion
+![image](photo_2023-01-06_00-30-33.jpg)
+<sub>pink hair guy in glasses, photograph, sporty body, cinematic lighting, clear eyes, perfect face, blush,  beautiful nose, beautiful eyes, detailed eyes</sub>
+
 
-Anime Diffusion is a latent text-to-image diffusion model trained on
+# Anime Diffusion
 
+Anime Diffusion is a latent text-to-image diffusion model trained on BLIP captions for Danbou set + Demon slayer + arts from 4ch
 
-# Gradio & Colab
 
 
 ## Model Description
@@ -47,7 +49,7 @@ pipe = StableDiffusionPipeline.from_pretrained(
 
 negative_prompt = """low-res, duplicate, poorly drawn face, ugly, undetailed face"""
 d = 'white girl'
-prompt = f"1girl, aqua eyes, baseball cap, blonde hair, closed mouth, earrings, green background, hat, hoop earrings, jewelry, looking at viewer, shirt, short hair, simple background, solo, upper body, yellow shirt" 
+prompt = f"pink hair guy in glasses, photograph, sporty body, cinematic lighting, clear eyes, perfect face, blush,  beautiful nose, beautiful eyes, detailed eyes" 
 num_samples = 1
 
 with  torch.inference_mode():
@@ -63,13 +65,14 @@ with  torch.inference_mode():
 images[0].save("test.png")
 ```
 
-## Team Members and Acknowledgements
+## Team Member and Acknowledgements
 
 This project would not have been possible without the incredible work by the [CompVis Researchers](https://ommer-lab.com/).
 
-- [Alex Wortega](https://github.com/AlexWortega) Open to work!!
+- [Alex Wortega](https://github.com/AlexWortega)
+<sub>alexwortega@yandex.ru</sub>
 
 
-In order to reach us, you can join our 
+In order to reach me, here is my blog:
 
 [![My tg channel]](https://t.me/lovedeathtransformers)